Semantic Content Search and Personalisation
Enhancing Content Discovery and User Engagement with AI-Powered Search
50% Reduction in Time Spent Searching Contents
The AI-powered semantic search feature allowed users to find relevant documents within the content libraries in less time, significantly reducing the time spent on manual searches by 50%.
25% Increase in User Engagement Metrics
Enabling users to find the content most useful to them using natural language led to a notable improvement in user engagement metrics.
Challenge
OnWellbeing faced challenges in manually managing and searching their extensive content libraries. The existing process was time-consuming and prone to human error, affecting their ability to provide personalised and timely information to users.
Process
Our team conducted a detailed assessment of OnWellbeing’s specific needs, identifying key requirements for automating content vectorisation and semantic search functionalities best suited to their existing technical infrastructure. We devised a phased approach, breaking down the project into key milestones with clear deliverables and timelines.
Solution
The project was broken down into three milestones:
Development of API Endpoints for Document Management: Created POST API endpoints for adding, deleting, and updating documents. This included vectorising and indexing content for efficient retrieval.
Implementation of a Semantic Search Feature: Developed GET API endpoints for AI-powered similarity search, enabling users to find relevant documents quickly.
Integration of AI-Driven Personalisation Tools: Utilised generative AI to provide personalised game summaries and reports, enhancing user engagement by delivering tailored insights
Summary
OnWellbeing implemented an AI-powered semantic search and personalisation system to improve content management. The solution reduced search time by 50% and increased user engagement by 25%. Key features included document management APIs, semantic search functionality, and AI-driven personalisation tools, resulting in more efficient content retrieval and tailored user experiences.
Semantic Content Search and Personalisation
Enhancing Content Discovery and User Engagement with AI-Powered Search
50% Reduction in Time Spent Searching Contents
The AI-powered semantic search feature allowed users to find relevant documents within the content libraries in less time, significantly reducing the time spent on manual searches by 50%.
25% Increase in User Engagement Metrics
Enabling users to find the content most useful to them using natural language led to a notable improvement in user engagement metrics.
Challenge
OnWellbeing faced challenges in manually managing and searching their extensive content libraries. The existing process was time-consuming and prone to human error, affecting their ability to provide personalised and timely information to users.
Process
Our team conducted a detailed assessment of OnWellbeing’s specific needs, identifying key requirements for automating content vectorisation and semantic search functionalities best suited to their existing technical infrastructure. We devised a phased approach, breaking down the project into key milestones with clear deliverables and timelines.
Solution
The project was broken down into three milestones:
Development of API Endpoints for Document Management: Created POST API endpoints for adding, deleting, and updating documents. This included vectorising and indexing content for efficient retrieval.
Implementation of a Semantic Search Feature: Developed GET API endpoints for AI-powered similarity search, enabling users to find relevant documents quickly.
Integration of AI-Driven Personalisation Tools: Utilised generative AI to provide personalised game summaries and reports, enhancing user engagement by delivering tailored insights
Summary
OnWellbeing implemented an AI-powered semantic search and personalisation system to improve content management. The solution reduced search time by 50% and increased user engagement by 25%. Key features included document management APIs, semantic search functionality, and AI-driven personalisation tools, resulting in more efficient content retrieval and tailored user experiences.
Semantic Content Search and Personalisation
Enhancing Content Discovery and User Engagement with AI-Powered Search
50% Reduction in Time Spent Searching Contents
The AI-powered semantic search feature allowed users to find relevant documents within the content libraries in less time, significantly reducing the time spent on manual searches by 50%.
25% Increase in User Engagement Metrics
Enabling users to find the content most useful to them using natural language led to a notable improvement in user engagement metrics.
Challenge
OnWellbeing faced challenges in manually managing and searching their extensive content libraries. The existing process was time-consuming and prone to human error, affecting their ability to provide personalised and timely information to users.
Process
Our team conducted a detailed assessment of OnWellbeing’s specific needs, identifying key requirements for automating content vectorisation and semantic search functionalities best suited to their existing technical infrastructure. We devised a phased approach, breaking down the project into key milestones with clear deliverables and timelines.
Solution
The project was broken down into three milestones:
Development of API Endpoints for Document Management: Created POST API endpoints for adding, deleting, and updating documents. This included vectorising and indexing content for efficient retrieval.
Implementation of a Semantic Search Feature: Developed GET API endpoints for AI-powered similarity search, enabling users to find relevant documents quickly.
Integration of AI-Driven Personalisation Tools: Utilised generative AI to provide personalised game summaries and reports, enhancing user engagement by delivering tailored insights
Summary
OnWellbeing implemented an AI-powered semantic search and personalisation system to improve content management. The solution reduced search time by 50% and increased user engagement by 25%. Key features included document management APIs, semantic search functionality, and AI-driven personalisation tools, resulting in more efficient content retrieval and tailored user experiences.